Search Results for "code review"

The claude-code-security-review repository implements a GitHub Action that uses Claude (via the Anthropic API) to perform semantic security audits of code changes in pull requests. Rather than relying purely on pattern matching or static analysis, this action feeds diffs and surrounding context to Claude to reason about potential vulnerabilities (e.g. injection, misconfigurations, secrets exposure, etc).

...Its default pipeline focuses on finding memory bugs in C and C++ code using ASAN as the crash detector. The overall architecture is meant to be adaptable, so teams can modify it for other languages, bug classes, and detection systems. Its main value is giving defenders a practical framework for exploring AI-assisted secure code review and remediation.

SkillSpector is a security scanner built to evaluate AI agent skills before they are installed or trusted. It helps teams inspect skills used by tools such as Claude Code, Codex CLI, and Gemini CLI. The project focuses on detecting vulnerabilities, malicious behavior, and risky patterns that may be hidden inside skill files. It combines fast static checks with optional LLM-based semantic review for issues that require deeper intent analysis. It supports several input types, including Git repositories, URLs, zip files, folders, and individual files. ...

...GitGot leverages the GitHub Search API to perform queries across repositories, files, and gists, allowing security researchers and penetration testers to discover sensitive information that may have been unintentionally exposed in public code. During a search session, users review results and provide feedback that allows GitGot to filter out irrelevant or repetitive findings. This feedback is used to build blacklists that eliminate results based on repository names, file names, user names, or fuzzy matches of file content. The approach helps reduce noise while guiding the search process toward more relevant results.